DRIVE OS Version: Drive OS 6.0.10 Target: aarch64 ** Issue Description:** We are trying to develop model to run on DLA. For this all the supported DLA operations are used. model.dla.bin.json { "dataConditionerParams": { "meanValue": [123.675, 116.28, 103.53], "stdev": [58.395, 57.12, 57.375]…

It is noticed that tensorRT_optimization tool generated DLA model does not seems to work with DNN APIs. Please use cuDLA APIs directly to run model on DLA.

Dear @atharv.sharma , What is the dwProcessorType used in dwDNN_initializeTensorRTFromFileWithEngineId and dlaEngine? Is it DW_PROCESSOR_TYPE_CUDLA and 0? If so, any dummy model can be shared to repro and investigate?

for platform VIBRANTE dwProcessorType is set as DW_PROCESSOR_TYPE_CUDLA and DLA engine has been set to 0. sample code: const dwProcessorType processor = useCuDla ? DW_PROCESSOR_TYPE_CUDLA : DW_PROCESSOR_TYPE_GPU; std::cout << "dwProcessorType: " << processor << "\n"; CHECK_DW_E…

Dear @SivaRamaKrishnaNV We found out the that the workflow for DLA compatible models to be accelerated in the following manner : use `trtexec` natively with the onnx model to generate a dla loadable variant of the model use `tensorRT_optimzation` tool to take the loadable compiled with the compile…

Dear @SivaRamaKrishnaNV Here’s what issue is - when native `trtexec` is used to compile the model for DLA hardware we see a reformat layer being added to reformat the inputs and outputs blob, and so when the ``tensorRT_optimzation` tool is used to wrap it for DNN APis, we see this benchdev2@tegra…

Dear @ashwin.nanda , Thank you for sharing model. Let me check and getback to you.

Dear @atharv.sharma @ashwin.nanda , Were you able to generate TRT model using tensorRT_optimzation tool with the shared ONNX file? I notice build issues. [image] atharv.sharma: usr/local/driveworks/tools/dnn/tensorRT_optimization --modelType=onnx --onnxFile=<path/to/model.onnx> --out=<path/to/…

Dear @SivaRamaKrishnaNV We were able to generate tensorrt compiled model by both trtexec binary and dw-tensorRT_optimization tool : The command used was ./tensorRT_optimization --modelType=onnx --onnxFile=/home/benchdev2/DLALaneNet/dla_lanenet_latest.onnx --inputIOFormats=fp16:chw16 --outputIOFor…

It looks like some issue with cuDLA lib calls when loading the model. I have filed internal bug to track this issue. I will keep you posted once I have an update.

cudlaModuleLoadFromMemory : load loadable failed. 7

Autonomous Vehicles DRIVE AGX Orin DRIVE AGX Orin General

atharv.sharma June 15, 2026, 8:40am 10

Dear @SivaRamaKrishnaNV any updates about this?

Using DLA hardware with DNN APIs

Topic		Replies	Views
Using DLA hardware with DNN APIs DRIVE AGX Orin General driveos-cudla	9	205	June 26, 2026
cuDLAStandaloneMode load model report error Container: CUDA cuda	8	1185	October 14, 2022
DLA:Using dla on orin nx meet an error Jetson Orin NX dla	7	253	October 29, 2024
Convert model to TensorRT with DLA \| DLA Node compilation Failed TensorRT	2	1042	August 12, 2021
NVMEDIA_DLA : 528, ERROR: load from memory failed DRIVE AGX Xavier General	2	676	August 31, 2022
Cannot build a TensorRT engine for DLA from a large ONNX file Jetson Xavier NX tensorrt , nvbugs , dla	11	2881	July 21, 2021
Trtexec failed to generate engine (Internal Error) with DLA Jetson Orin NX tensorrt , nvbugs , dla	7	1291	April 8, 2024
Running tensorflow models on DLA Jetson AGX Xavier	8	1855	July 24, 2019
How to enable DLA? DRIVE AGX Orin General driveworks	4	239	December 9, 2024
TensorRT run DLA on Xavier Jetson AGX Xavier nvbugs	10	1870	April 21, 2020

cudlaModuleLoadFromMemory : load loadable failed. 7

Related topics